In November 2024, Model Context Protocol (MCP) was introduced by Anthropic (opens in a new tab). Since then, it's gone from niche spec to the connective tissue of the AI stack.
Retool works with MCP in two directions:
- You can now connect AI tools like Claude Code, Cursor, or Codex directly to your Retool workspace through Retool's own native MCP server to build apps, run queries, and manage your organization without leaving your AI tool.
- You can connect external MCP servers to your Retool agents and apps, giving them tools like Jira, Linear, or GitHub to create tickets, update docs, and act on data across your stack.
In this piece, we're going to cover both integration paths. First, we'll look at how to build Retool apps, run queries, and manage your organization without leaving your AI coding agent. Along with that, you'll learn everything about Retool's MCP server—what it unlocks, how its permission scopes work, and how to connect any MCP-compatible client to your Retool workspace. Then, we'll walk through a couple of different setup options for connecting your Retool agents and apps to external tools.
What is MCP?
MCP (Model Context Protocol) is an open standard that allows AI agents to connect to external tools and data sources, such as GitHub, Jira, or Figma, through a consistent, standardized interface, without custom-built integrations for each tool.
It works through MCP servers: an MCP server is how a piece of software exposes its functionality to a large language model. The server describes its tools in a standard format, and any MCP-compatible client can discover those tools and call them. A great example is GitHub's MCP server (opens in a new tab). Point an AI agent at this MCP server, and it can read issues, search code, and open pull requests, with no glue code on your end.
Why does MCP matter for agents?
This functionality matters for AI agents because access to tools is what separates a chatbot from something that does real work. An agent with MCP connections can pull live data from the systems your team already uses and act on your behalf within them.
How to use Retool as a native MCP server
Retool now operates as a native MCP server, generally available on Cloud and on self-hosted deployments running version 4.86 or later and available on all plans, with some administrative tools limited to Business and Enterprise plans.
Any MCP-compatible AI tool, including Claude, Cursor, Codex, ChatGPT, Gemini, Kiro, and VS Code, can connect directly to your Retool workspace and work with your apps, resources, workflows, permissions, and users, based on the permission scope you authorize. This is the reverse of the integrations above: instead of Retool agents reaching out to external tools, external AI tools reach into Retool.
The practical effect is that Retool comes to wherever you build. If you spend your day in Claude Code or Cursor, you can inspect your Retool environment, kick off app builds, and handle admin tasks without switching to a browser.
What can you do with Retool's MCP server?
With Retool's MCP server connected, an AI assistant can work directly against your Retool workspace. The available tools fall into three groups
Building. You can build apps from your chosen development environment:
- Start a new app build from a natural-language prompt, or continue an existing one
- Import an existing React app into Retool
- View past and current agent activity on a build, and cancel a failed build
- Read an app's files and inspect existing apps
- Manually review function runs
- Create resources and write queries against connected resources, like Retool Database, to power data analysis
- Publish apps and manage who can open them
Managing your organization. Admins can handle operational work without opening Retool:
- Bulk-invite users and manage pending invites
- Audit which users have access to the organization
- Disable users who no longer need access, or reset a user's two-factor authentication
- Create permission groups and custom roles, and manage group membership and role assignments
- Check who can access an app, resource, or workflow, and grant or remove access
- Investigate audit logs
- List and inspect workflows, folders, environments, and organization settings
- List all connected resources and see their configurations
Managing resources. You can work with your data sources from the same session:
- List all connected resources and see their configurations
- Create and update resources
- Write queries against connected resources, like Retool Database, to power data analysis
Some tools depend on your Retool plan. Audit logs and object-level permissions require a Business or Enterprise plan, and permission groups and custom roles require Enterprise. If your plan doesn't include a tool, it won't appear in your client's tool list.
The full list of supported tools is in the MCP tools reference, or you can connect the server and run tools/list.
What AI tools can connect to Retool via MCP?
Any MCP-compatible AI client can connect to Retool's MCP server. Retool documents setup instructions for these clients:
- Claude Code, via
claude mcp add - Claude (Desktop or browser), found by searching for Retool under Customize > Connectors on Free, Pro, and Max plans. On Team and Enterprise plans, an Owner or Primary Owner adds it as a custom connector.
- Cursor, via its MCP settings or
.cursor/mcp.json - Codex, via
codex mcp add - ChatGPT, by adding an MCP server under Settings > Plugins
- Gemini CLI, via
gemini mcp add, and Gemini Enterprise, as a custom MCP server data store - Kiro, via the Kiro CLI
- VS Code, with GitHub Copilot Chat (VS Code 1.102 or later)
- Retool Agents themselves, which can consume Retool's MCP server as a tool like any other
The ecosystem of MCP clients is growing quickly. For current setup instructions per client, see Retool's MCP documentation.
How to connect your AI tool to Retool's MCP server
Every client connects with the same three details:
- Endpoint URL:
https://mcp.retool.com/mcpon Cloud. Self-hosted instances use their own domain, such ashttps://example.retool.com/mcp. - Transport: HTTP
- Authentication: OAuth 2.0
During the OAuth flow, a browser window opens. On Cloud, you first enter your organization URL, or choose an organization you're already signed into, and sign in. Then you select the scopes you want to authorize. After authenticating, you may need to restart your coding agent.
Here's what that looks like in Claude Code:
claude mcp add --transport http retool https://mcp.retool.com/mcpStart a new session, run https://retool.com/mcp, select the retool server, and complete the OAuth flow in your browser. The MCP is then ready to use. The flow for Cursor, Codex, ChatGPT, Gemini, Kiro, and VS Code follows the same pattern with each tool's own configuration syntax; the docs have step-by-step instructions for each.
On Cloud, no hosting or deployment is required on your end. Retool hosts the MCP server for you. On self-hosted instances running version 4.86 or later, the MCP server runs as a separate service that an administrator enables and routes traffic to, following the self-hosted setup guide. The app-building tools also need the new app builder's supporting services (the agent sandbox, Temporal, and a code or JS executor) to be running.
Understanding Retool's three MCP scopes
Retool's MCP server offers three permission scopes that control what an AI tool can see and do inside your workspace: mcp:read for read-only access, mcp:write for building and executing, and mcp:admin for organization management, which only org administrators can select. You choose scopes during the OAuth flow when you connect a client.
mcp:read: Read-only visibility into your workspace
The mcp:read scope gives an AI assistant a read-only view of your Retool workspace. It can list and retrieve apps and resources, see who can open apps you own or administer, generate TypeScript definitions for connected resources, and read the history and status of app build threads. Nothing in this scope can change anything, which makes it the right starting point for evaluating the integration or for teams that only need visibility into Retool.
mcp:write: Build apps and run queries from your AI tool
The mcp:write scope is where app building happens. With it authorized, an AI assistant can create or update a Retool app from a natural-language prompt, monitor the build as it progresses, respond to review requests, and cancel activity that's gone sideways. It can also import existing apps, publish apps, and grant or revoke access to them. On the data side, it can create and update resources and execute TypeScript against connected resources, which is how you run data analysis queries from within your AI tool.
mcp:admin: Organization management for administrators
The mcp:admin scope covers governance and is available exclusively to Retool organization administrators. It adds the ability to list, retrieve, and delete workflows; manage user provisioning and pending invites; disable users and reset two-factor authentication; manage permission groups, custom roles, and object-level access; view folders, environments, and organization settings; and investigate audit logs. Because this scope grants operational control across your workspace, authorize it deliberately and only where admin-level work from an AI tool is actually the goal.
How Retool enforces MCP permission boundaries
Retool enforces permission boundaries at the MCP layer. You can't be granted a scope with more permissions than your Retool account allows; only organization administrators can select mcp:admin, for example. And the MCP server surfaces only objects, such as apps, resources, and workflows, that the authenticated user already has permission to view.
In practice, this means your AI assistant gets the same view of Retool you already have, and nothing more. For teams evaluating MCP adoption, that's the important guardrail: connecting an AI tool doesn't widen anyone's access, because every request inherits the access controls, audit trails, and data permissions your organization has already configured at the platform level.
How to connect a public MCP server to your Retool agent
The most straightforward option is a server that's already publicly hosted. Some software providers, like Atlassian, have set up and configured their own remote MCP server (opens in a new tab). You connect it to an AI tool like Claude or Retool Agents, authenticate with OAuth, and immediately get access to data from Jira, Confluence, and other services. Your agents can then create Jira tickets, update Confluence docs, and work with data that already lives in Atlassian.
To set this up in Retool, you configure the MCP server as a resource and add it to your agent:
- From Retool Home, open the Resources tab and click Create new → Resource. Select MCP Server as the resource type.
- Give the resource a name and description, and enter the server's public URL.
- Configure authentication. Select Automatic, the recommended option, and click Auto-configure authentication. Retool detects whether the server requires authentication at all and pre-fills what it finds. A server with no auth, like the AWS Knowledge MCP server (opens in a new tab) (
https://knowledge-mcp.global.api.aws), needs no credentials. For a server that uses OAuth, like Linear's (https://mcp.linear.app/mcp), Retool discovers the OAuth 2.0 settings and, if the server supports client registration, registers a client for you. Click Connect with OAuth to finish. You may see a consent screen asking you to authorize Retool with the service. For servers that use a static username and password or a token, choose Basic Auth or Bearer Token instead. - Click Test Connection to confirm the server responds, then create the resource.
Now add the server to your agent. From your agent's configuration screen, click Add new tool, choose Connect to MCP server, and select your new resource from the dropdown. Once saved, every tool the MCP server exposes shows up in your agent's tool list, and the agent calls the appropriate one when a task requires it.
Whether you invoke your agent via chat, email, or a workflow, it can now use any tool available on the MCP server. No additional configuration required.
Using external MCP servers in Retool apps
MCP Server resources work in apps too. You can prompt the app-building agent to use an MCP server as context while it builds, or have it write a function that calls the server's tools at runtime, so your app's users can work with those tools as well. In functions, each MCP Server resource is available as a typed client with one method per tool. If the resource uses OAuth 2.0, each user who runs the function connects their own account, because tool calls use that user's credentials. For details, see Connect to an external MCP server.
What if the MCP server you want doesn't have a public URL?
Many MCP servers (opens in a new tab) still exist primarily as GitHub repos, designed to run locally over stdio on your own machine. Local servers work fine for a desktop AI client, but they aren't reachable from the public internet, so Retool agents (or any cloud-hosted LLM) can't connect to them directly.
To use one of these servers with Retool, it needs to be running somewhere Retool can reach over HTTPS, using MCP's Streamable HTTP or Server-Sent Events (SSE) transport. On Cloud, that means a public URL; on self-hosted Retool, the endpoint only needs to be reachable from your instance's network. For production use, you have two realistic paths: find a hosted version of the server through a registry like Smithery, or host the server yourself and point Retool at your deployment. For quick testing, you can also expose a local server through a temporary gateway.
How to test a local MCP server through a gateway
If you want to try a local server with an agent, or give the app-building agent extra context during a build session, you can expose it through an HTTP gateway. Retool's docs walk through using supergateway to serve a local stdio server over SSE, then ngrok, protected with basic auth, to give it a public URL that you enter as the resource's server URL. The server is only reachable while your machine and the gateway are running, so use a stable, remote HTTPS endpoint for anything persistent.
How to find and connect hosted MCP servers with Smithery
Smithery (opens in a new tab) is the largest open registry of MCP servers. erver authors publish their work for distribution, and each server gets a dedicated page with connection details. Smithery's gateway sits in front of published servers and handles MCP protocol compliance, OAuth flows, and the configuration UI, making it a convenient source of connectable endpoints for Retool. The official MCP Registry (opens in a new tab) is another place to find servers.
To connect a Smithery-published server to Retool:
- Find the server in Smithery's registry (opens in a new tab) and open its server page.
- Copy the server's HTTP endpoint from the connection details.
- In Retool, create an MCP Server resource as described above, set the Server URL to the endpoint, and configure authentication. Servers that require API keys or OAuth surface through Smithery's authentication flow.
- Test the connection, create the resource, and add it to your agent as a tool.
If the server you want isn't in the registry and only exists as a repo, you'll need to host it yourself. Deploy it to any platform that can serve Streamable HTTP or SSE over a public HTTPS URL, then add that URL to Retool as an MCP Server resource. Once it's running, you can also publish it on Smithery (opens in a new tab) so others can discover it, and so Smithery's gateway can handle OAuth and configuration for you.
One caveat: Smithery also distributes local stdio servers as MCPB bundles. Those run inside desktop clients like Claude Desktop, not on a server, so they can't be used as Retool resources. For Retool, you need an endpoint with a URL.
Retool as both MCP consumer and MCP server: the full picture
Retool's MCP integration now works in both directions at once. On one side, Retool agents and apps connect to external MCP servers, pulling in tools like GitHub, Jira, or Figma to act on data across your stack. On the other, Retool exposes its own workspace to any MCP-compatible AI tool that speaks the protocol.
The two patterns are complementary, and teams will often run both. One developer wires a hosted Linear MCP server into a Retool agent that triages support tickets. At the same time, a teammate uses Claude Code with Retool's MCP server to build the app that displays them. You can even point a Retool agent at Retool's own MCP server, giving an agent inside Retool programmatic access to the workspace around it.
Which direction you start with depends on where your AI workflow begins: inside Retool, or outside it.
Next steps with MCP in Retool
Whether you're connecting external tools to your Retool agents and apps or connecting your AI tools to Retool, here's where to start.
To connect an external MCP server to Retool:
- Find a public MCP server endpoint (like Linear's at
https://mcp.linear.app/mcp), or a hosted server through Smithery's registry (opens in a new tab) - Create an MCP Server resource in Retool and configure authentication
- Add the MCP server as a tool in your Retool agent, or prompt the app builder to use it in an app
To connect your AI tool to Retool via Retool's MCP server:
- Add
https://mcp.retool.com/mcpto your MCP-compatible client (self-hosted instances usehttps://<your-retool-instance>/mcponce an admin enables the MCP service) - Authenticate with OAuth 2.0, choose your organization, and select your permission scopes
- Start building apps, running queries, and managing your workspace from your AI tool of choice
For full setup instructions and the latest compatibility information, see the Retool MCP documentation. And if you're ready to go deeper on building AI agents that do real work inside your business, explore our Agents & Workflows tutorial collection.
This article was originally published in June 2026. It was most recently updated in November 2026.